Quick/Comparisons
15 | Gaming | 35 |
25 | Workstation | 38 |
21 | AI/ML |
Compare with something else?
Compare Apple M4 GPU with another →32 |
95 | Energy Efficiency | 63 |
32 | Quick Comparison Final Score | 36 |
| Custom | Graphics Processor | AD107 |
| 1280 | Cores | 3072 |
| 80 / 40 | TMUs / ROPs | 96 / 48 |
| 1062.09 | Blender GPU | 3125.73 |
| — | Tomb Raider | 116 |
| — | Average FPS | 95 |
| — | Forza Horizon 5 | 80 |
| — | The Witcher 3 | 115 |
| — | Counter-Strike 2 | 155 |
| — | Far Cry 6 | 99 |
| — | Hogwarts Legacy | 64 |
| — | Call of Duty | 90 |
| — | Ghost of Tsushima | 61 |
| — | Cyberpunk 2077 | 75 |
| — | 1080p High | 115 |
| — | 1080p Ultra | 95 |
| — | 1440p Ultra | 69 |
| — | 4K Ultra | 39 |
| — | Margin of Error | Low |
| 37678 | GB6 Compute Score | 106633 |
| 72.2 img/sec | Background Blur | 186.9 img/sec |
| 48.3 img/sec | Face Detection | 112.7 img/sec |
| 1.4 Gpixels/sec | Horizon Detection | 3.92 Gpixels/sec |
| 1.94 Gpixels/sec | Edge Detection | 5.16 Gpixels/sec |
| 1.5 Gpixels/sec | Gaussian Blur | 4.94 Gpixels/sec |
| 0.53 Gpixels/sec | Feature Matching | 1.34 Gpixels/sec |
| 123.3 Gpixels/sec | Stereo Matching | 446.2 Gpixels/sec |
| 4938.4 FPS | Particle Physics | 14935.1 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 19523 |
| — | G2D Mark | 1039 |
| — | DirectX 11 | 174 FPS |
| — | DirectX 12 | 76 FPS |
| — | GPU Compute | 9185 Ops/s |
| 10346 | GB6 ML Single Precision | 17857 |
| 11883 | GB6 ML Half Precision | 29214 |
| 11036 | GB6 ML Quantized | 14234 |
| 4874 | Image Classification (SP) | 7696 |
| 8168 | Image Segmentation (HP) | 13706 |
| 11983 | Image Super Resolution (Q) | 23289 |
| 17036 | Face Detection (HP) | 31126 |
| 31171 | Pose Estimation (Q) | 78361 |
| 2964 | Text Classification (SP) | 3315 |
| 3410 | Machine Translation (HP) | 3491 |
| 5112 | Object Detection (SP) | 9386 |
| 22700 | Depth Estimation (Q) | 36778 |
| 60872 | Style Transfer (SP) | 148120 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 59 GPixel/s | Pixel Fill Rate | 118 GPixel/s |
| 118 GTexel/s | Texture Fill Rate | 236 GTexel/s |
| 3.8 TFLOPS | FLOPS (FP32) | 15.1 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 8 GB |
| 7500 MHz | Memory Clock | — |
| 15000 Mbps | Effective Memory Speed | — |
| 128-bit | Bus | 128-bit |
| No | ECC | No |
| 120 GB/s | Memory Bandwidth | 272 GB/s |
| Custom | Interface | PCIe 4.0 x8 |
| 18 W | TGP | 115 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 5 nm |
| — | Die Size | 159 mm² |
| 28 billion | Transistor Count | 18 billion |
| — | Transistor Density | 113.21 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 3 |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| May 7, 2024 | Released | May 18, 2023 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Ada Lovelace |
| Custom | GPU Codename | AD107 |
| -Apple M4 (10-Core)or above | Recommended CPU | -Intel Core i5 14600Kor above |
| 4097 | Steel Nomad Lite Score | 10683 |
| — | Time Spy | 10619 |
| 16545 | Solar Bay | 49280 |
| — | Port Royal | 6054 |
| — | Fire Strike | 28548 |
| 9591 | Wild Life Extreme | 20605 |
| — | Night Raid | 121586 |
| 500 MHz | Base Clock | 1830 MHz |
| 1470 MHz | Boost Clock | 2460 MHz |
| 1280 | Shading Units | 3072 |
| 80 | Texture Mapping Units (TMUs) | 96 |
| 40 | Render Output Units (ROPs) | 48 |
| 160 | Compute Units (Pipelines) | 24 |
| — | Tensor Cores | 96 |
| — | Ray-tracing Cores | 24 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 24MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |